Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36264
    Prev
    Next
    INDEX
    Explanations

    Express/Node.js bodyParser

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circa
    -0.07
    ゥ
    -0.07
    一如
    -0.07
    essential
    -0.06
    aph
    -0.06
    _plus
    -0.06
    Ⲉ
    -0.06
     счит
    -0.06
    .eulerAngles
    -0.06
    吸取
    -0.06
    POSITIVE LOGITS
    -NLS
    0.07
     keyboard
    0.07
    年中国
    0.06
    でお
    0.06
     interruption
    0.06
    Projectile
    0.06
     ''↵
    0.06
    :['
    0.06
    假
    0.06
     Yog
    0.06
    Activations Density 0.000%

    No Known Activations